Child Mind Institute and Kaggle Launch Competition to Predict Teen Internet Addiction

Citizen scientists will use Healthy Brain Network data on physical activity and internet use; competition sponsored by Dell Technologies and NVIDIA

New York, NY —  The youth mental health crisis has many causes, but one rising concern is technology. Mobile phones and social media are front and center in bestselling books, alerts from the US Surgeon General, and discussions in local school districts. The internet is a vital tool for education, entertainment, and connection. On the flip side, tech addiction—or problematic internet use (PIU) — is associated with family dysfunction, substance use, and mental health problems like anxiety and depression.

Identifying young people who are vulnerable to PIU and connecting them to care are central to recent research on this topic. But current methods for measuring PIU are complex and require professional assessments. To accelerate this work, the Child Mind Institute and Kaggle are launching a competition, using deidentified data from the Child Mind Institute Health Brain Network study, to develop a predictive model that can identify early signs of PIU using physical activity and fitness measures. The competition, sponsored by Dell Technologies and NVIDIA, will launch on September 19th at 11:30AM and run for 3 months.

“Physical and fitness measures are extremely accessible and widely collected,” explains Michelle Freund, PhD, director of Strategic Data Initiatives at the Child Mind Institute. “If we can use these biosignatures to create tools that help clinicians identify young people at risk and encourage healthier digital habits, it could have a population level impact. And I think Kaggle community members will be incredibly excited to dig into the Healthy Brain Network dataset, which is a uniquely rich resource that makes this kind of work possible.”

The Child Mind Institute Healthy Brain Network is the most comprehensive study of child and adolescent brain and behavior in the United States, built on a community recruitment model that has provided thousands of families with mental health and learning evaluations. Over 350 papers related to the Healthy Brain Network have been published. For this competition, users will focus on Internet Addiction Test (IAT) scores and physical activity and fitness assessments, including questionnaires (e.g., sleep length and quality), clinical measurements (e.g., weight, heart rate, body composition), physical fitness (e.g., grip-strength) and objective physical activity measured through a wearable device. Contestants working with this rich dataset will have wide latitude to identify the most effective measurements or combinations of measurements for predicting IAT scores.

“Open Science principles have been central to the impact of the Child Mind Institute on global scientific accessibility, reproducibility, collaboration, and innovation,” says Michael P. Milham, MD, PhD, Phyllis Green and Randolph Cowen Scholar and Chief Science Officer at the Child Mind Institute. “Transforming the culture of mental health research — including by opening up our rich datasets to a massively inclusive science and engineering collaboration — is the key to accelerating scientific innovation and discovery in child mental health and learning, bringing the very best insights immediately and directly into the care of children.”

“Improving teen mental health is one of today’s greatest challenges, and NVIDIA is collaborating with Dell Technologies and the Child Mind Institute to equip the Kaggle community with cutting-edge data science libraries and tools to help tackle this critical problem,” said John Zedlewski, senior director for accelerated data science at NVIDIA. “NVIDIA accelerated computing has long bolstered efficient, creative solutions to Kaggle challenges. Accelerated data science enables faster build and test cycles, so Kagglers can get to their solutions faster.”

Kaggle is the world’s largest data science community, offering tools and resources to develop data science projects. Kaggle competitions are open to all participants, regardless of their level of experience or expertise, leading to a broad spectrum of solutions and approaches. And the data resources and solutions become part of a learning community, contributing to innovation and problem-solving long after the competition has closed. The Healthy Brain Network dataset has previously been used in a Kaggle competition to detect sleep onset from accelerometer data, with more than 38,000 submissions.

About Kaggle

Kaggle is the world’s largest online data science competition community. With more than 4 million members across 194 countries, the Kaggle community uses its diverse set of academic backgrounds to solve complex data science problems. Working as individuals or in teams, the winning competitors are awarded prizes and industry recognition for their accomplishments.

About the Healthy Brain Network

The Healthy Brain Network is a community-based research initiative of the Child Mind Institute. We provide no-cost, study-related mental health and learning evaluations to children ages 5-21 and connect families with community resources. We are collecting the information needed to find brain and body characteristics that are associated with mental health and learning disorders. The Healthy Brain Network stores and openly shares de-identified data about psychiatric, behavioral, cognitive, and lifestyle (e.g., fitness, diet) phenotypes, as well as multimodal brain imaging (MRI), electroencephalography (EEG), digital voice and video recordings, genetics, and actigraphy.

Visit the Healthy Brain Network community website and scientific data portal.

About the Child Mind Institute

We are the leading independent nonprofit in children’s mental health providing gold-standard, evidence-based care, delivering educational resources to millions of families each year, training educators in underserved communities, and developing open science initiatives and tomorrow’s breakthrough treatments.

Visit Child Mind Institute on social media: Instagram, Facebook, Twitter, LinkedIn

For press questions, contact our press team at childmindinstitute@ssmandl.com or our media officer at mediaoffice@childmind.org.